© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 534
    Prev
    Next
    INDEX
    Explanations

    paste and copy actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OOD
    -0.26
     chaos
    -0.23
    enums
    -0.23
    饨
    -0.23
     molest
    -0.23
     epoch
    -0.23
    funcs
    -0.23
    ]:=
    -0.22
    eton
    -0.22
     vend
    -0.22
    POSITIVE LOGITS
    ä¸ĭéĿ¢
    0.32
     underneath
    0.26
    imu
    0.25
    æīĢæıIJä¾ĽçļĦ
    0.25
    orna
    0.25
    佩æĪ´
    0.25
    strup
    0.24
    Provid
    0.24
    æıIJä¾ĽçļĦ
    0.23
     below
    0.23
    Activations Density 0.018%

    No Known Activations